Can Recursive Self-Report Probing Detect Emergent Misalignment?

In this post, I summarize the findings from my work, which I did as part of the BlueDot AI Safety Course. The full code is available here. BackgroundBetley et al. (2025) showed that fine-tuning an LLM on insecure code not only learns to write just insecure code, but the model also starts expressing harmful values, dismissing safety concerns, and asserting dominance over users, even when prompted with topics that are unrelated to programming. Thus, this work begs the question of how one can know ...